Abstract
This paper investigates the usefulness of multi-fractal analysis and local binary patterns (LBP) as texture descriptors for classifying mammogram images into different breast density categories. Multi-fractal analysis is also used in the pre-processing step to segment the region of interest (ROI). We use four multi-fractal measures and the LBP method to extract texture features, and to compare their classification performance in experiments. In addition, a feature descriptor combining multi-fractal features and multi-resolution LBP (MLBP) features is proposed and evaluated in this study to improve classification accuracy. An autoencoder network and principal component analysis (PCA) are used for reducing feature redundancy in the classification model. A full field digital mammogram (FFDM) dataset, INBreast, which contains 409 mammogram images, is used in our experiment. BI-RADS density labels given by radiologists are used as the ground truth to evaluate the classification results using the proposed methods. Experimental results show that the proposed feature descriptor based on multi-fractal features and LBP result in higher classification accuracy than using individual texture feature sets.
Highlights
The α-histogram is used as the texture feature descriptor to represent the breast density related features
The multi-resolution LBP (MLBP) descriptor contains much more image features extracted from larger local areas, and as expected, produces a better classification performance
The best classification accuracy of 84.6% is obtained using the Iso+MLBP feature descriptor
Summary
Breast density is a critical bio-marker which indicates the possibility of developing breast cancer in the future for women. High breast density is caused by a high percentage of fibro-glandular tissue and reduces the effectiveness of mammography screening [1]. Related research work shows that women with extremely dense breast could suffer four to six-fold higher risk of developing breast cancer than other females with low breast density [2]. Dense tissue areas in mammograms cause the ‘masking’ effect leading to reduced sensitivity when radiologists visually assess breast lesions or early signs of cancer, such as lumps and calcification clusters [3]. Breast density is gaining significant attention because it is closely associated with higher cancer risk, increased incidence of interval cancer and reduced mammographic sensitivity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
